🤖 Machine Learning Overview
What is Machine Learning?
"Machine learning is a subset of artificial intelligence that focuses primarily on creating algorithms
that enable a computer to learn from data and previous experiences independently."
Machine learning allows computers to automatically learn from previous data and improve their
performance without being explicitly programmed.
How does Machine Learning work?
Machine learning systems build prediction models, learn from previous data, and predict new data
output. The amount of data helps to build a better model that accurately predicts the output, which
in turn affects the accuracy of the predicted output.
Features of Machine Learning
Data-driven technology: Machine learning uses data to detect various patterns in a given
dataset.
Automatic learning: It can learn from past data and improve automatically.
Similar to data mining: Machine learning deals with huge amounts of data.
Need for Machine Learning
The demand for machine learning is steadily rising because it can perform tasks that are too complex
for a person to directly implement. Machine learning is required because humans are constrained by
their inability to manually access vast amounts of data.
📊 Types of Machine Learning
Classification of Machine Learning
Machine learning can be classified into three types:
Type Description
Supervised Sample-labeled data are provided to the machine learning system for training,
Learning and the system then predicts the output based on the training data.
A machine learns without any supervision. The training is provided to the
Unsupervised machine with a set of data that has not been labeled, classified, or
Learning categorized.
Reinforcement A feedback-based learning method, in which a learning agent gets a reward for
Learning each right action and gets a penalty for each wrong action.
📚 History of Machine Learning
1950s: The Beginning:
Alan Turing: Proposed the concept of a machine that can learn (Turing Test) in his seminal
paper "Computing Machinery and Intelligence".
Arthur Samuel: Developed the first self-learning program, a checkers-playing program, which
used a method now known as reinforcement learning.
1960s-1970s: Early Development:
Perceptron: Introduced by Frank Rosenblatt, the perceptron was an early neural network
model designed to recognize patterns.
Tom M. Mitchell: Published a book titled "Machine Learning", which became one of the
foundational texts for the field.
1980s-1990s: Growth and Challenges:
Backpropagation: The development of the backpropagation algorithm significantly improved
the training of neural networks, leading to the resurgence of interest in neural networks.
Statistical Learning Theory: Vladimir Vapnik and Alexey Chervonenkis developed the theory
that laid the groundwork for support vector machines (SVMs).
2000s: Rise of Big Data and Deep Learning:
Big Data: The explosion of digital data and advances in computing power allowed for the
development of more complex models.
Deep Learning: The resurgence of neural networks, now with many layers (deep learning),
revolutionized fields such as image and speech recognition.
2010s-Present: Ubiquity of Machine Learning:
AI and ML in Everyday Life: Machine learning has become integral to various industries,
including healthcare, finance, and transportation. Technologies like autonomous vehicles,
personal assistants (e.g., Siri, Alexa), and recommendation systems have become common.
